相关标准及路由器测试

1、2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 1 1第八章第八章 网络设备测试网络设备测试测试标准及路由器测试测试标准及路由器测试o目标目标：n了解相关标准了解相关标准n学习路由器的常用指标学习路由器的常用指标及测试方法及测试方法 o主要内容主要内容n1 相关标准相关标准n2 测量方法概述测量方法概述n3 路由器的性能指标路由器的性能指标n4 路由器性能测试路由器性能测试n5 测试实例测试实例2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 2 21

2、1 相关标准相关标准oRFC2544RFC2544 (Benchmarking Methodology for Network (Benchmarking Methodology for Network Interconnect Devices)Interconnect Devices)oRFC2889RFC2889（BenchmarkingBenchmarkingMethodologyMethodologyforforLANLANSwitchingSwitchingDevicesDevices）oYD/T1156-2001YD/T1156-2001路由器测试规范高端路由器路由器测试规范高端路

3、由器oYD/T1098-2001YD/T1098-2001路由器测试规范低端路由器路由器测试规范低端路由器oYD/T1141-2001YD/T1141-2001 千兆比以太网交换机测试方法千兆比以太网交换机测试方法oYD/T1142-2001YD/T1142-2001 IP IP电话网守设备技术要求及测试方法电话网守设备技术要求及测试方法oYD/T1072-2000YD/T1072-2000 IP IP电话网关设备测试方法电话网关设备测试方法oYD/T1075-2000YD/T1075-2000 网络接入服务器（网络接入服务器（NASNAS）测试方法）测试方法oYD/T1171-2001 IP

4、YD/T1171-2001 IP网络技术要求网络技术要求网络性能参数与指网络性能参数与指标标2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 3 3相关标准相关标准- -续续oYD/T1251.1-2003YD/T1251.1-2003 路由协议一致性测试方法路由协议一致性测试方法中间中间系统到中间系统路由交换协议（系统到中间系统路由交换协议（IS-IS) IS-IS) oYD/T1251.2-2003YD/T1251.2-2003 路由协议一致性测试方法路由协议一致性测试方法开放开放最短路径优先协议（最短路径优先协议（OS

5、PFOSPF） oYD/T1251.3-2003YD/T1251.3-2003 路由协议一致性测试方法路由协议一致性测试方法边界边界网关协议（网关协议（BGP4BGP4） oYD/T1260-2003YD/T1260-2003 基于端口的虚拟局域网（基于端口的虚拟局域网（VLANVLAN）技术）技术要求和测试方法要求和测试方法oYD/T1033-2000YD/T1033-2000 传输性能的指标系列传输性能的指标系列oYD/T10912000YD/T10912000 56kbit/s 56kbit/s调制解调器接口及传输性能调制解调器接口及传输性能技术要求和测试方法技术要求和测试方法2022-

6、7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 4 4Request for Comments: 2544Request for Comments: 2544oNetwork Working GroupNetwork Working Group， Benchmarking Benchmarking Methodology for Network Interconnect DevicesMethodology for Network Interconnect Devices， S. BradnerS. Bradner， Harvard

7、 UniversityHarvard University， J. McQuaidJ. McQuaid， NetScout SystemsNetScout Systems， March 1999March 1999oThis document discusses and defines a number of This document discusses and defines a number of tests that may be used to describe the perfo-tests that may be used to describe the perfo-rmance

8、 characteristics of a network intercon-rmance characteristics of a network intercon-necting device. necting device. In addition to defining the In addition to defining the tests this document also describes specific tests this document also describes specific formats for reporting the results of the

9、 tests. formats for reporting the results of the tests. 2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 5 5RFC2544 Benchmarking tests 1RFC2544 Benchmarking tests 1： ThroughputThroughputoDefinition:Definition: The maximum rate at which none of the The maximum rate at which none of the off

10、ered frames are dropped by the offered frames are dropped by the device.device.o详见：详见：RFC 1242RFC 1242o吞吐量测试可以确定被测试设备吞吐量测试可以确定被测试设备(DUT)(DUT)或被或被测试系统测试系统(SUT)(SUT)在不丢弃包的情况下所能支在不丢弃包的情况下所能支持的吞吐速率。持的吞吐速率。o二分法二分法2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 6 6Throughput test-ProcedureThro

11、ughput test-ProcedureoSend a specific number of frames at a Send a specific number of frames at a specific rate through the DUT and then count specific rate through the DUT and then count the frames that are transmitted by the DUT. the frames that are transmitted by the DUT. oIf the count of offered

12、 frames is equal to If the count of offered frames is equal to the count of received frames, the fewer the count of received frames, the fewer frames are received than were transmitted, frames are received than were transmitted, the rate of the offered stream is reduced the rate of the offered strea

13、m is reduced and the test is rerun. and the test is rerun. oThe throughput is the fastest rate at which The throughput is the fastest rate at which the count of test frames transmitted by the the count of test frames transmitted by the DUT is equal to the number of test frames DUT is equal to the nu

14、mber of test frames sent to it by the test equipment.sent to it by the test equipment.2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 7 7RFC2544 Benchmarking tests 2RFC2544 Benchmarking tests 2： LatencyLatencyDefinition:Definition:oFor For store and forward devicesstore and forward devic

15、es: : The time interval starting when the The time interval starting when the last bit of the last bit of the input frameinput frame reaches the input port and ending when the reaches the input port and ending when the first bit of the output framefirst bit of the output frame is seen on the output

16、is seen on the output port.port.oFor For bit forwarding devicesbit forwarding devices: : The time interval starting when The time interval starting when the end of the first bit the end of the first bit of the input frameof the input frame reaches the input port and ending reaches the input port and

17、 ending when when the start of the first bit of the output framethe start of the first bit of the output frame is is seen on the output port.seen on the output port. 由此定义看：仅包括排队和处理时延，不包括传输时延？由此定义看：仅包括排队和处理时延，不包括传输时延？2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 8 8延时测试延时测试o延时测试延时测试测量一台

18、测量一台DUT DUT 在有负载条件下转发数据包所需在有负载条件下转发数据包所需的时间。的时间。SmartApplications SmartApplications 在规定时间内生成在规定时间内生成100%100%的负载的负载( (或者按测试设置中规定的比例或者按测试设置中规定的比例) )。在测试过程中，。在测试过程中，SmartApplications SmartApplications 测量每对端口上的每一个包的延测量每对端口上的每一个包的延时。时。o对于对于存储转发（存储转发（Store-and-forwardStore-and-forward）设备来说，测量设备来说，测量的延时是指从

19、输入帧的最后一个比特达到输入端口的时的延时是指从输入帧的最后一个比特达到输入端口的时刻到输出帧的第一个比特出现在输出端口上的时刻的时刻到输出帧的第一个比特出现在输出端口上的时刻的时间间隔。对于间间隔。对于cut-throughout cut-throughout 设备来说，延时是指从设备来说，延时是指从输入帧的第一比特达到输入端口的时刻到输出帧的第一输入帧的第一比特达到输入端口的时刻到输出帧的第一比特出现在输出端口的时刻的间隔。测试设置中规定的比特出现在输出端口的时刻的间隔。测试设置中规定的每一种包长度都要进行延时测试。每一种包长度都要进行延时测试。 2022-7-22022-7-2西安电子科

20、技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 9 9Latency test-Procedure:Latency test-Procedure:oSend a stream of frames at a particular frame size Send a stream of frames at a particular frame size through the DUT at the determined throughput rate to a through the DUT at the determined throughput rate to a

21、 specific destination. The stream SHOULD be at least specific destination. The stream SHOULD be at least 120 seconds in duration. 120 seconds in duration. oAn identifying tag SHOULD be included in one frame An identifying tag SHOULD be included in one frame after 60 seconds with the type of tag bein

22、g after 60 seconds with the type of tag being implementation dependent. The time at which this implementation dependent. The time at which this frame is fully transmitted is recorded (frame is fully transmitted is recorded (timestamp Atimestamp A). ). The receiver logic in the test equipment MUST Th

23、e receiver logic in the test equipment MUST recognize the tag information in the frame stream and recognize the tag information in the frame stream and record the time at which the tagged frame was received record the time at which the tagged frame was received ( (timestamp Btimestamp B).).oThe late

24、ncy is timestamp B minus timestamp AThe latency is timestamp B minus timestamp A。RFC 1242RFC 1242oThe test MUST be repeated at least 20 times with the The test MUST be repeated at least 20 times with the reported value being the average of the recorded reported value being the average of the recorde

25、d values.values.2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 1010RFC2544 Benchmarking tests 3RFC2544 Benchmarking tests 3： Frame loss rateFrame loss rateoDefinition:Definition: Percentage of frames Percentage of frames thatthat should have been should have been forwarded by a network

26、device under steady state forwarded by a network device under steady state (constant) load(constant) load thatthat were not forwarded due to were not forwarded due to lack of resourceslack of resources. .（如何理解两个如何理解两个that? that? 并列修饰。并列修饰。）oRFC 1242RFC 1242o包丢失测试通过测量由于缺少资源而未转发的包的包丢失测试通过测量由于缺少资源而未转发的

27、包的比例来显示高负载状态下比例来显示高负载状态下DUTDUT的性能。的性能。2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 1111Frame Loss rate-test ProcedureFrame Loss rate-test ProcedureoSend a Send a specific number of framesspecific number of frames at a at a specific ratespecific rate through the DUT to be tested and co

28、unt the frames that through the DUT to be tested and count the frames that are transmitted by the DUT. The frame loss rate at are transmitted by the DUT. The frame loss rate at each point is calculated using the following equation:each point is calculated using the following equation: ( ( input_coun

29、t - output_count ) ( ( input_count - output_count ) * * 100 ) / input_count 100 ) / input_countoThe first trial SHOULD be run for the frame rate that The first trial SHOULD be run for the frame rate that corresponds to 100% of the maximum rate for the frame corresponds to 100% of the maximum rate fo

30、r the frame size on the input media. Repeat the procedure for the size on the input media. Repeat the procedure for the rate that corresponds to 90% of the maximum rate used rate that corresponds to 90% of the maximum rate used and then for 80% of this rate. This sequence SHOULD and then for 80% of

31、this rate. This sequence SHOULD be continued (at reducing 10% intervals) until there be continued (at reducing 10% intervals) until there are two successive trials in which no frames are lost.are two successive trials in which no frames are lost. 2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室

32、朱畅华朱畅华 1212RFC2544 Benchmarking tests 4RFC2544 Benchmarking tests 4： Back-to-backBack-to-backoDefinition:Definition:nFixed length frames presented at a rate Fixed length frames presented at a rate such that there is the minimum legal such that there is the minimum legal separation for a given medium

33、 between separation for a given medium between frames over a short to medium period of frames over a short to medium period of time, starting from an idle state.time, starting from an idle state.nMeasurement units: Number of N-octet Measurement units: Number of N-octet frames in burstframes in burst

34、oRFC1242RFC12422022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 1313背靠背性能测试背靠背性能测试o背靠背性能测试通过背靠背性能测试通过以最大帧速率发送以最大帧速率发送突发传输流突发传输流并并测量无包丢失时的最大突发（测量无包丢失时的最大突发（BurstBurst）长度）长度( (总包总包数量数量) )来测试来测试DUTDUT的缓冲区容量。的缓冲区容量。oSmartApplications SmartApplications 在全负载条件下生成突发传输在全负载条件下生成突发传输流，如果所有的包都得到转发，就

35、增加突发长度，流，如果所有的包都得到转发，就增加突发长度，并重新进行测试。但是，如果某一对端口上出现包并重新进行测试。但是，如果某一对端口上出现包丢失，丢失，SmartApplicationsSmartApplications将突发长度减少一半并将突发长度减少一半并再次进行测试。然后，再次进行测试。然后，SmartApplicationsSmartApplications利用二利用二分搜索查找无包丢失时的最大突发长度。测试设置分搜索查找无包丢失时的最大突发长度。测试设置中规定的每一种包长度都要进行背到背性能测试。中规定的每一种包长度都要进行背到背性能测试。2022-7-22022-7-2西安电

36、子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 1414Back-to-backtest procedureBack-to-backtest procedureoSend a burst of frames with minimum inter-frame gaps Send a burst of frames with minimum inter-frame gaps to the DUT and count the number of frames forwarded by to the DUT and count the number of frames

37、 forwarded by the DUT. If the count of transmitted frames is equal the DUT. If the count of transmitted frames is equal to the number of frames forwarded the to the number of frames forwarded the length of the length of the burstburst is increased and the test is rerun. is increased and the test is

38、rerun.oIf the number of forwarded frames is less than the If the number of forwarded frames is less than the number transmitted, the number transmitted, the length of the burstlength of the burst is is reduced and the test is rerun.reduced and the test is rerun.oThe back-to-back value is the number

39、of frames in the The back-to-back value is the number of frames in the longest burst that the DUT will handle without the longest burst that the DUT will handle without the loss of any frames.loss of any frames. The trial length MUST be at least The trial length MUST be at least 2 seconds and SHOULD

40、 be repeated at least 50 times 2 seconds and SHOULD be repeated at least 50 times with the average of the recorded values being reported.with the average of the recorded values being reported.2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 1515RFC2544 Benchmarking tests 5RFC2544 Benchmar

41、king tests 5： System recoverySystem recoveryoObjective:Objective: To characterize the speed at which a To characterize the speed at which a DUT recovers from an overload condition.DUT recovers from an overload condition.oProcedure:Procedure: First determine the throughput for a First determine the t

42、hroughput for a DUT at each of the listed frame sizes. Send a DUT at each of the listed frame sizes. Send a stream of frames at a rate 110% of the recorded stream of frames at a rate 110% of the recorded throughput rate or the maximum rate for the throughput rate or the maximum rate for the mediamed

43、ia（线速）（线速）, whichever is lower, for at least , whichever is lower, for at least 60 seconds. At 60 seconds. At Timestamp ATimestamp A reduce the frame reduce the frame rate to 50% of the above rate and record the rate to 50% of the above rate and record the time of the last frame lost (time of the la

44、st frame lost (Timestamp BTimestamp B). ). The The system recovery time is determined by system recovery time is determined by subtracting Timestamp B from Timestamp A.subtracting Timestamp B from Timestamp A.2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 1616RFC2544 Benchmarking tests

45、6RFC2544 Benchmarking tests 6：ResetResetoObjective:Objective: To characterize the speed at which a DUT To characterize the speed at which a DUT recovers from a device or software reset.recovers from a device or software reset.oProcedure:Procedure: First determine the throughput for the DUT First det

46、ermine the throughput for the DUT for the minimum frame size on the media used in the for the minimum frame size on the media used in the testing. Send a continuous stream of frames at the testing. Send a continuous stream of frames at the determined throughput rate for the minimum sized frames. det

47、ermined throughput rate for the minimum sized frames. Cause a reset in the DUT. Monitor the output until Cause a reset in the DUT. Monitor the output until frames begin to be forwarded and record the time that the frames begin to be forwarded and record the time that the last frame (Timestamp A) of

48、the initial stream and the last frame (Timestamp A) of the initial stream and the first frame of the new stream (Timestamp B) are received.first frame of the new stream (Timestamp B) are received.oThe reset value is obtained by subtracting Timestamp A The reset value is obtained by subtracting Times

49、tamp A from Timestamp B. from Timestamp B. oHardware and software resets, as well as a power Hardware and software resets, as well as a power interruption SHOULD be tested. interruption SHOULD be tested. 2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 1717转发能力测试实例转发能力测试实例o思博伦（思博伦（Spirent

50、Spirent）通）通信的信的SmartBits 6000BSmartBits 6000Bo依据依据RFC 2544RFC 2544完成完成n吞吐率吞吐率n延迟延迟n帧丢失率帧丢失率nBack to BackBack to Back测试测试 2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 18183 3 路由器的测试指标路由器的测试指标o1 1、吞吐量、吞吐量：吞吐量是指路由器的包转发能力。吞吐量与路由器的：吞吐量是指路由器的包转发能力。吞吐量与路由器的端口数量、端口速率、数据包长度、数据包类型、路由计算模式端口数量、端口

51、速率、数据包长度、数据包类型、路由计算模式（分布或集中）以及测试方法有关，一般泛指处理器处理数据包（分布或集中）以及测试方法有关，一般泛指处理器处理数据包的能力。高速路由器的包转发能力至少应在的能力。高速路由器的包转发能力至少应在2020包包/ /秒以上。秒以上。o端口吞吐量端口吞吐量： 端口吞吐量是路由器在某端口上的包转发能力。通常采用两端口吞吐量是路由器在某端口上的包转发能力。通常采用两个相同速率测试接口。一般测试接口可能与接口位置及关系相关，个相同速率测试接口。一般测试接口可能与接口位置及关系相关，例如同一插卡上端口间测试的吞吐量可能与不同插卡上端口间吞例如同一插卡上端口间测试的吞吐量可

52、能与不同插卡上端口间吞吐量值不同。吐量值不同。整机吞吐量整机吞吐量： 整机吞吐量是指设备整机的包转发能力，是设备性能的重要整机吞吐量是指设备整机的包转发能力，是设备性能的重要指标。路由器的工作在于根据指标。路由器的工作在于根据IPIP包头或者包头或者MPLSMPLS（多协议标签交换）（多协议标签交换）标记选路，因此性能指标是指每秒转发包的数量。整机吞吐量通标记选路，因此性能指标是指每秒转发包的数量。整机吞吐量通常小于路由器所有端口吞吐量之和。常小于路由器所有端口吞吐量之和。 2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华

53、1919路由器的测试指标路由器的测试指标o2 2、背板能力、背板能力：背板指输入与输出端口间的物理通：背板指输入与输出端口间的物理通路。路。o背板能力是路由器的内部实现，传统路由器采用共背板能力是路由器的内部实现，传统路由器采用共享背板，但是应用于高性能路由器时不可避免的会享背板，但是应用于高性能路由器时不可避免的会遇到拥塞问题，其次也很难设计出高速的共享总线，遇到拥塞问题，其次也很难设计出高速的共享总线，所以现有的高速路由器一般采用可交换式背板的设所以现有的高速路由器一般采用可交换式背板的设计。计。o背板能力通常大于依据吞吐量和测试包长所计算的背板能力通常大于依据吞吐量和测试包长所计算的值。

54、但是背板能力只能在设计中体现，一般无法测值。但是背板能力只能在设计中体现，一般无法测试。试。 （电磁兼容性设计电磁兼容性设计）2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 2020路由器的测试指标路由器的测试指标o3 3、丢包率、丢包率：丢包率是指路由器在稳定的持：丢包率是指路由器在稳定的持续负荷下，由于资源缺少而不能转发的数据续负荷下，由于资源缺少而不能转发的数据包在应该转发的数据包中所占的比例。包在应该转发的数据包中所占的比例。n丢包率通常用作衡量路由器在超负荷工作时路丢包率通常用作衡量路由器在超负荷工作时路由器的性

55、能由器的性能。n丢包率与数据包长度以及包发送频率相关丢包率与数据包长度以及包发送频率相关，在，在一些环境下，可以加上路由抖动或大量路由后一些环境下，可以加上路由抖动或大量路由后进行测试模拟。进行测试模拟。2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 2121路由器的测试指标路由器的测试指标o4 4、时延以及时延抖动、时延以及时延抖动：时延是指数据包第一个比：时延是指数据包第一个比特进入路由器到最后一个比特从路由器输出的时间特进入路由器到最后一个比特从路由器输出的时间间隔。该时间间隔是存储转发方式工作的路由器的间隔。该时间

56、间隔是存储转发方式工作的路由器的处理时间。时延与数据包的长度和链路速率都有关，处理时间。时延与数据包的长度和链路速率都有关，通常在路由器端口吞吐量范围内进行测试。通常在路由器端口吞吐量范围内进行测试。o时延对网络性能影响较大时延对网络性能影响较大, , 对高速路由器，在最差对高速路由器，在最差情况下情况下, , 要求对要求对15181518字节及以下的字节及以下的IPIP包时延均都小包时延均都小于于1ms1ms。o时延抖动是指时延的变化时延抖动是指时延的变化。数据业务对时延抖动不。数据业务对时延抖动不敏感，所以该指标通常不作为衡量高速路由器的重敏感，所以该指标通常不作为衡量高速路由器的重要指标

57、。对要指标。对IPIP上除数据外的其它业务，如语音、视上除数据外的其它业务，如语音、视频业务，该指标才有测试的必要性（频业务，该指标才有测试的必要性（VoIPVoIP）。）。2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室 朱畅华朱畅华 2222路由器的测试指标路由器的测试指标o5 5、路由表容量、路由表容量：路由器通常依靠所建立及维护的：路由器通常依靠所建立及维护的路由表来决定包的转发。路由表能力是指路由表内路由表来决定包的转发。路由表能力是指路由表内所容纳路由表项数量的极限。所容纳路由表项数量的极限。o由于在由于在InternetIn

58、ternet上执行上执行BGPBGP（边界网关协议）的路（边界网关协议）的路由器通常拥有数十万条路由表项，所以该项目也是由器通常拥有数十万条路由表项，所以该项目也是路由器能力的重要体现。路由器能力的重要体现。o一般而言，一般而言，高速路由器应该能够支持至少高速路由器应该能够支持至少2525万条路万条路由由，平均每个目的地址至少提供平均每个目的地址至少提供2 2条路径条路径，系统必，系统必须支持至少须支持至少2525个个BGPBGP对等以及至少对等以及至少5050个个IGPIGP邻居。邻居。 2022-7-22022-7-2西安电子科技大学西安电子科技大学ISNISN国家重点实验室国家重点实验室

59、 朱畅华朱畅华 2323路由器的测试指标路由器的测试指标o6 6、QoSQoS（服务质量）能力（服务质量）能力：主要用于度量与某种业：主要用于度量与某种业务相关的一整套性能。务相关的一整套性能。n队列管理机制队列管理机制：队列管理控制机制通常指路由器拥塞管：队列管理控制机制通常指路由器拥塞管理机制及其队列调度算法。常见的方法有理机制及其队列调度算法。常见的方法有REDRED（随机早期（随机早期预测）、预测）、WREDWRED（加权随机预测）、（加权随机预测）、WRRWRR（加权轮询）、（加权轮询）、WFQWFQ（加权平均队列）、以及改进后的加权公平流排队算（加权平均队列）、以及改进后的加权公平流排队算法法WF2QWF2Q等。等。n排队策略排队策略：支持公平排队算法，支持加权公平排队算法。：支持公平排队算法，支持加权公平排队算法。该算法给每个队列一个权（该算法给每个队列一个权（weightweight），由它决定该队列），由它决定该队列可享用的链路带宽。这样，实时业务可以确实得到所要可享用的链路带宽。这样，实时业务可以确实得到所要求的性能，非弹性业务流可以与普通（求的性能，非弹性业务流可以与普通（Best-effortBest-effort）业）业务流相互隔离。务流相互隔离。2022-7-22022-7-2西安电子科技大学西安电子科技